5 Ways to Serve Open Source LLMs (With Code Examples)

In the ever-evolving realm of Large Language Models (LLMs), the tools and techniques for serving them are advancing at a pace as swift as the models themselves. Unlike conventional models like…

3 Best Methods for Spatial Interpolation

Interpolation is a quite common mathematical concept, which is used not only by data scientists, but also people from a vast range of fields. However, when dealing with geospatial data, interpolation…

The Math Behind Convolutional Neural Networks

Dive into CNN, the backbone of Computer Vision, understand its mathematics, implement it from scratch, and explore its applications.

Mastering RAG Systems: From Fundamentals to Advanced, with Strategic Component Evaluation

Guide to master RAG systems, from basic to advanced, with techniques like windowing, hybrid search, query rewriting, routing, and component evaluation.

How I Became a Data Scientist as an International Student with Broken English

Currently, I am a data scientist over 4 years of experience. I want to delve into my own journey — a gradual process of discovering my passion for data science. It took me quite a while to figure out…

How to Work Remotely and Not Feel Isolated

It’s not a secret that many vacancies in IT & data are remote. On one hand, this means not wasting time in traffic jams on the way to work and back home. But on the other hand, for many employees the…

How to Build a Generative AI Tool for Information Extraction from Receipts

Paper receipts come in all sorts of styles and formats and represent an interesting target for automated information extraction. They also provide a wealth of itemized costs that, if aggregated into…

Linear Regressions for Causal Conclusions

I suppose most of us have heard the statement “correlation doesn’t imply causation” multiple times. It often becomes a problem for analysts since we frequently can see only correlations but still…

Design an Easy-to-Use Deep Learning Framework

Deep learning frameworks are extremely transitory. If you compare the deep learning frameworks people use today with what it was eight years ago, you will find the landscape is completely different…

Overwriting in Python: Tricky. Dangerous. Powerful

I’ve overwritten plenty of various objects in Python. If you’ve spent your share of hours coding in Python, you have, too. This is because, at least in Python, overwriting objects lies at the core of…